This model is designed to train the next generation of xAIs large language model (LLM), Grok.
This weekend, the@xAIteam brought our Colossus 100k H100 training cluster online.
From start to finish, it was done in 122 days.
Colossus is the most powerful AI training system in the world.
Moreover, it will double in size to 200k (50k H200s) in a few months.
From start to finish, it was done in 122 days.
Colossus is the most powerful AI training system in the world.
Moreover, it will double in size to 200K (50K H200s) in a few months.
Exciting to see Colossus, the worlds largest GPU #supercomputer, come online in record time.
Colossus is powered by @nvidias #acceleratedcomputing platform, delivering breakthrough performance with exceptional gains in #energyefficiency.
Congratulations to the entire team!
NVIDIA Data Centres X handle wrote on its platform.
He said it expects to release xAIs third-generation AI model, Grok-3, by December.
